Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3803 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.9940. Min Act: -0.1700
Data Index: 4753255 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.9315. Min Act: -0.1700
Data Index: 7394334 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.9315. Min Act: -0.1700
Data Index: 3597748 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.8065. Min Act: -0.1700
Data Index: 5258665 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.7752. Min Act: -0.1700
Data Index: 5987789 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.7752. Min Act: -0.1700
Data Index: 7061739 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.7440. Min Act: -0.1700
Data Index: 4745277 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.7440. Min Act: -0.1700
Data Index: 6017351 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.7127. Min Act: -0.1700
Data Index: 4588430 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.6815. Min Act: -0.1700
Data Index: 8715299 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.6502. Min Act: -0.1700
Data Index: 4730947 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.6502. Min Act: -0.1700
Data Index: 5443097 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.5877. Min Act: -0.1700
Data Index: 7563199 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.6190. Min Act: -0.1700
Data Index: 3215107 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.6190. Min Act: -0.1700
Data Index: 4714811 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.5877. Min Act: -0.1700
Data Index: 6754939 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.5877. Min Act: -0.1700
Data Index: 8095238 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.5565. Min Act: -0.1700
Data Index: 3482158 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.6190. Min Act: -0.1700
Data Index: 421099 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9940. Min Range: -6.9940
Max Act: 6.5877. Min Act: -0.1700
Data Index: 5527655 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19